CN109767438A - A kind of thermal-induced imagery defect characteristic recognition methods based on dynamic multi-objective optimization - Google Patents
A kind of thermal-induced imagery defect characteristic recognition methods based on dynamic multi-objective optimization Download PDFInfo
- Publication number
- CN109767438A CN109767438A CN201910019827.XA CN201910019827A CN109767438A CN 109767438 A CN109767438 A CN 109767438A CN 201910019827 A CN201910019827 A CN 201910019827A CN 109767438 A CN109767438 A CN 109767438A
- Authority
- CN
- China
- Prior art keywords
- thermal response
- transient thermal
- transient
- pixel
- column
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Landscapes
- Radiation Pyrometers (AREA)
- Investigating Or Analyzing Materials Using Thermal Means (AREA)
Abstract
The thermal-induced imagery defect characteristic recognition methods based on dynamic multi-objective optimization that the invention discloses a kind of, by converting the transient thermal response that step-length selects pixel to thermal image sequence, and classified using FCM, obtain the generic of the transient thermal response of each pixel, then consider the pixel value similitude of each classification pixel Yu similar pixel, and the otherness with different classes of pixel, construct corresponding multiple objective function, simultaneously, after every secondary environment changes, pass through forecasting mechanism, channeling direction is provided for Evolution of Population, multi-objective optimization algorithm is helped to make quick response to new change, obtain the dimensionality reduction result of thermal image sequence, the defect characteristic of thermal-induced imagery is finally extracted using Pulse Coupled Neural Network, to realize the accurate selection for representing thermal transient corresponding (temperature spot), it ensure that scarce The precision of feature extraction is fallen into, while reducing to obtain each classification information under dynamic environment and represent thermal transient and calculating consumption accordingly.
Description
Technical field
The invention belongs to defect detecting technique fields, more specifically, are related to a kind of based on dynamic multi-objective optimization
Thermal-induced imagery defect characteristic recognition methods.
Background technique
Thermal-induced imagery detection technique obtains material by the thermal field variation of control thermal excitation method and measurement material surface
Surface and its surface structural information below, to achieve the purpose that detection.When obtaining structural information, infrared heat is usually used
As the thermal field information that instrument record surface of test piece or sub-surface change over time, and it is converted into thermal image sequence and shows
Come.Since the data volume of the thermal image sequence obtained with thermal infrared imager is huge, noise jamming is strong, in order to obtain better detection
Effect needs to carry out feature extraction to thermal image sequence.
When handling thermal image sequence, there is the method based on single-frame images processing, also there is the side based on image sequence processing
Method.Method based on single-frame images processing only considered test specimen in the temperature distribution information at some moment, can not embody examination
Part in the temperature conditions of different moments, obtained processing result be it is incomplete, it is unilateral.Therefore based on image sequence processing
Method has obtained extensive concern and research.
What infrared thermal imaging detection was commonly used is vortex thermal imaging.According to the law of electromagnetic induction, when the friendship for being passed through high frequency
When the induction coil of time-dependent current is close to conductor test specimen (abbreviation test specimen), vortex can be generated on the surface of test specimen.If in test specimen
Defective, vortex will be forced to change its flow direction, this will be so that measured piece internal vortex density changes around defect.By coke
Ear law is converted into Joule heat it is found that being vortexed in test specimen, causes the heat generated in test specimen uneven, to generate high-temperature region
And low-temperature space, due to the otherness of temperature, high-temperature region heat, to low temperature block transitive, leads to test specimen different zones temperature by heat transfer
Degree changes, and the change procedure of test specimen temperature is acquired by thermal infrared imager, then gives the thermal image sequence of acquisition to meter
Calculation machine is analyzed and processed, and to obtain test specimen relevant information, realizes the qualitative and quantitative detection of defect.
On October 30th, 2018 announce, publication No. CN108712069A, it is entitled " one kind based on row variable step divide
In the Chinese invention patent application of the high-pressure bottle thermal imaging imperfection detection method cut ", dimension-reduction treatment is carried out to cluster result, and
Defect characteristic is extracted after two-dimensional matrix and original image the sequences transformation obtained with dimensionality reduction.In this process, difference is utilized
The degree of correlation between classification obtains the representative temperature spot of every one kind, but without research represent temperature spot (transient thermal response) with it is similar
The similitude of temperature spot, the representative temperature spot selected is not enough to characterize such feature, therefore needs while considering otherness and phase
Like target of the property in terms of the two.In addition, this method is the thermal response temperature that search has regional representativeness in each category
Point, the temperature spot are screening and other cluster centre distances and maximum thermal response data, the generation of all categories in corresponding classification
The thermal response data of table temperature spot constitute a two-dimensional matrix, and then these represent temperature spot is to the information representation of corresponding classification
It is incomplete, therefore the defect characteristic by extracting after linear transformation is inaccurate, so that certain precision be not achieved.
In real world, many multi-objective optimization questions are protected from environmental, and optimization problem itself, independent variable etc. can be with
The variation of environment and change.In this process, by using Multipurpose Optimal Method, comprehensively consider different classes of difference
Anisotropic and generic similitude obtains the approximate forward position solution of each category temperature point, randomly chooses one from these forward position solutions
A temperature spot is used as and represents temperature spot.In the case where not considering the ideal conditions of factor of environment, acquisition can comprehensively characterize each class
The representative temperature spot of other information, but if in a dynamic environment, each time in the environment of be carried out and entire calculate step, time
Consumption is big and reaction is slow.
Summary of the invention
The infrared heat based on dynamic multi-objective optimization that it is an object of the invention to overcome the deficiencies of the prior art and provide a kind of
Image deflects characteristic recognition method reduces under dynamic environment while improving defect characteristic extraction precision, obtains each class
Other information represents the calculating consumption of thermal transient corresponding (temperature spot).
For achieving the above object, the present invention is based on the thermal-induced imagery defect characteristic identification sides of dynamic multi-objective optimization
Method, which comprises the following steps:
(1), the thermal image sequence that thermal infrared imager obtains is indicated with three-dimensional matrice S, element S (i, j, t) table therein
Show the i-th row of the t frame thermal image of thermal image sequence, the pixel value of jth column;
(2), max pixel value S (i is selected from three-dimensional matrice Szz,jzz,tzz), wherein izz、jzzAnd tzzRespectively indicate maximum
The frame number of pixel value pixel line number of the row, the columns of column and place frame;
(3), for the t of three-dimensional matrice SzzFrame chooses jthzzRow chooses P according to the variation of pixel value (i.e. temperature value)
A pixel value trip point, trip point are located between two jump pixel value pixels, are carried out by row to three-dimensional matrice S with trip point
It divides, obtains P+1 row data block;
In p-th of row data block SpIn (p=1,2 ..., P+1), find max pixel value, be denoted asIts
In,Respectively indicate p-th of row data block SpThe columns of middle max pixel value pixel line number of the row, column
And the frame number of place frame, then max pixel valueCorresponding transient thermal response isT=1,
2 ..., T, T are the total quantity of three-dimensional matrice S frame;
P-th of row data block S is setpTemperature threshold be THREp, calculate transient thermal responseMost with distance
Big pixel value, that is, temperature maximumPixel column from the near to the distant ring by the corresponding thermal transient of pixel pixel value
It answersBetween degree of correlation Reb, b successively takes 1,2 ..., and judges degree of correlation RebWhether temperature threshold is less than
THREp, when being less than, stop calculating, at this point, pixel spacing b is p-th of row data block row data block SpRow step-length, be denoted as
CLp;
(4), for the t of three-dimensional matrice SzzFrame chooses i-thzzRow chooses Q according to the variation of pixel value (i.e. temperature value)
A pixel value trip point, trip point are located between two jump pixel value pixels, are carried out by column to three-dimensional matrice S with trip point
It divides, obtains Q+1 column data block;
In q-th of column data block SqIn (q=1,2 ..., Q+1), find max pixel value, be denoted asIts
In,Respectively indicate q-th of column data block SqThe columns of middle max pixel value pixel line number of the row, column
And the frame number of place frame, then max pixel valueCorresponding transient thermal response isT=1,
2 ..., T, T are the total quantity of three-dimensional matrice S frame;
Q-th of column data block S is setqTemperature threshold be THREq, calculate transient thermal responseMost with distance
Big pixel value, that is, temperature maximumThe pixel corresponding thermal transient of pixel pixel value from the near to the distant of being expert at is rung
It answersBetween degree of correlation Red, d successively takes 1,2 ..., and judges degree of correlation RedWhether temperature threshold is less than
THREq, when being less than, stop calculating, at this point, pixel spacing d is d-th of column data block SqColumn step-length, be denoted as CLq;
(5), piecemeal substep is long chooses transient thermal response
(5.1), the K pixel value that the P pixel value trip point chosen according to step (3) is chosen by column and step (4)
Trip point carries out piecemeal to three-dimensional matrice S by row, obtains a data block of (P+1) × (Q+1), pth, upper q-th of the data of column on row
Block is expressed as Sp,q;
(5.2), for each data block Sp,q, threshold value DD is set, set number g=1, initialized pixel point are initialized
Set i=1, j=1, and by max pixel value S (izz,jzz,tzz) corresponding transient thermal response S (izz,jzz, t), t=1,2 ...,
T is stored in set X (g);Then data block S is calculatedp,qMiddle pixel is located at i row, the transient thermal response S of j columnp,q(i,j,
T), t=1, the degree of correlation Re between 2 ..., T, with set X (g)i,j, and judge:
If Rei,j< DD, then g=g+1, and by transient thermal response Sp,q(i, j, t), t=1,2 ..., T are new as one
Characteristic storage is in set X (g);Otherwise, i=i+CL is enabledp, continue to calculate next transient thermal response Sp,q(i, j, t), t=1,
2 ..., the degree of correlation of T and set X (g);If i > Mp,q, then i=i-M is enabledp,q, j=j+CLq, that is, change to jth+CLqArrange into
Row calculates, if j > Np,q, then transient thermal response is chosen and is finished, wherein Mp,q、Np,qRespectively data block Sp,qLine number, column
Number;
(6), all set X (g) the i.e. transient thermal response for all a data blocks of (P+1) × (Q+1) for choosing step (5)
L class is divided into using FCM (fuzzy C-means clustering) algorithm, obtains classification belonging to each transient thermal response;
(7), the representative of every class transient thermal response is chosen based on dynamic multi-objective, and constitutes matrix Y
(7.1), under the m+1 times external environment, when being represented to the choosing of a class transient thermal response of i-th ' (i'=1 ..., L),
Define multiple objective function:
Wherein,The transient thermal response selected for the i-th ' class transient thermal response under the m+1 times external environmentClass in Euclidean distance, indicate are as follows:
The transient thermal response selected for the i-th ' class transient thermal responseL-1
Euclidean distance between class, Euclidean distance between L-1 class calculatedComposition is renumberd,It indicates
Are as follows:
For transient thermal responseIn pixel value, that is, temperature value of t moment,For the i-th ' class thermal transient
Respond cluster centre t moment pixel value, that is, temperature value,It is jth ' class transient thermal response cluster centre in t
Pixel value, that is, the temperature value at moment;
(7.2), the multiple objective function approximation forward position disaggregation obtained under the m-1 times and m secondary environment is respectivelyWithCorresponding population transient thermal response (temperature spot) disaggregation is respectivelyWithIts number is respectivelyWithAfter environmental change, according to the m-1 times and the historical information of m secondary environment, prediction calculates close under m+1 secondary environment
Like the initialization population transient thermal response of forward position disaggregation, steps are as follows:
(7.2.1)、Be fromSolution concentrates random selection NEA transient thermal responseThe transient thermal response of composition
Collection, n'=1,2 .., NE, calculateThe number W for representing transient thermal response is concentrated, it is multi-party under m+1 secondary environment for obtaining
To forecast set:
Wherein, W1And W2It is W lower limit value and upper limit value respectively, and has W1=L+1, W2=3L,It is the variation of m secondary environment
The assessed value of degree, is obtained by following formula:
Wherein,Be fromSolution concentrates random selection NEA transient thermal responseThe transient thermal response of composition
Collection, n'=1,2 .., NE;
(7.2.2), selection W represents transient thermal response
A), when initial, the multi-direction forecast set of PS of transient thermal response composition is representedConsist of two parts:
First is thatThe center of disaggregation transient thermal response, is denoted as
Wherein,For disaggregationIn n-th of transient thermal response;
Second is that PF (the optimal forward position the Pareto) minimax solution obtained under m secondary environment, is denoted as
For the number of minimax solution;
At this point, setThe middle number for representing transient thermal responseFor L'+1;
B), disaggregation is calculatedIn n-th of transient thermal responseTo setIn each representative
Transient thermal responseEuclidean distanceAnd it will be every according to Euclidean distance
It is aIt is divided into apart from the smallest cluster set represented where transient thermal responseIn;
C) if,Then exportAnd cluster resultIfIt needs to increase newly and represents transient thermal responseIt is rung as thermal transient is represented
Set should be stored inIn,It is obtained by following formula:
Wherein,It isA cluster resultRepresentative transient state
Thermal response,It isA cluster resultRepresent transient state k-th
Thermal response;Find each cluster resultMiddle transient thermal responseTransient state is represented with corresponding
Thermal responseThe maximum transient thermal response of distance, such a cluster result just obtains one apart from maximum thermal transient
Then response, total W find one apart from maximum transient thermal response at this W again and maximum represent thermal transient as increasing newly
ResponseThen return step C);
(7.2.3), the multi-direction forecast set of PS according to the m-1 times and m secondary environment
WithWherein,According to step (7.2.1), (7.2.2)
Method obtains, and W' isConcentrate the number for representing transient thermal response;
Calculate prediction direction
Wherein,It is the multi-direction forecast set of PSIn withApart from nearest transient thermal response, serial number
h';
When (7.2.4), the number of iterations g'=0, the initialization population thermal transient of the approximate forward position disaggregation under m+1 secondary environment
Response number is Np, whereinA initial population transient thermal response generates at random in value range,At the beginning of a
Beginning population transient thermal response is predicted to obtain by following formula:
Wherein, wnFor transient thermal responseAffiliated cluster resultSerial number,It is one to obey
Value is 0, and variance isNormal distribution random number, varianceCalculation formula are as follows:
(7.3), relevant parameter is initialized
Initialize the number of iterations g'=0, one group of equally distributed weight vectorsWherein,
Initialized reference point
It is functionCorresponding reference point;Maximum number of iterations g'max;
The evolutionary rate for initializing each population transient thermal response isPopulation thermal transient is rung
The global optimum answered and local best-fit
(7.4), it utilizesConstruct the dynamic mesh of each population transient thermal response under Tchebycheff polymerization
Scalar functions fitness value
(7.5), to n=1 ..., NP: according to particle swarm algorithm renewal speedWith population transient thermal responseCompare according to multi-objective optimization algorithmUpdate global optimumLocal optimumAnd reference pointFromMiddle reservation dominatesSolution vector, remove all quiltsThe solution vector of domination, ifIn vector all
It does not dominateIt willIt is addedN=n+1 simultaneously, if n≤NP, then g'=g'+1;
(7.6), it evolves and terminates judgement: if g'≤g'max, then repeatedly step (7.5), if g'> g'max, then the i-th ' class is obtained
The final forward position approximation disaggregation of temperature transient thermal response
(7.7), from forward position approximate solution collectionSelect the representative of the i-th ' class transient thermal responsei'REP, the transient state of all L classes
Thermal response, which is represented, places (one is classified as the pixel value i.e. temperature value at T moment) by column, constitutes the matrix Y of a T × L;
(8), by each frame in three-dimensional matrice S since first row, latter column are connect at the end of previous column, are constituted new
A column, obtain the corresponding T column pixel value of T frame, then, according to time order and function, T column pixel value be sequentially placed, constitutes I × J
Row, T column two dimensional image matrix O, carry out linear transformation to two-dimensional matrix O with matrix Y, it may be assumed thatObtain two dimensional image
Matrix R, whereinIt is the pseudo inverse matrix of matrix Y, O for L × T matrixTThe transposed matrix of two dimensional image matrix O, obtained two dimension
Image array R is L row, I × J column;
Every a line of two dimensional image matrix R is intercepted by J Leie, and the J of interception is arranged to be sequentially placed by row, constitutes one
I × J two dimensional image is opened, such L row obtains L I × J two dimensional images, these pictures all contain defect area, for convenience of lacking
Outline identification is fallen into, a two dimensional image of defect area and non-defective region pixel value (temperature value) disparity is selected, and is remembered
For f (x, y);
(9), feature identification is carried out to two dimensional image f (x, y) using Pulse Coupled Neural Network (PCNN), obtains defect spy
Sign:
(9.1), construct a PCNN network by I × J neuron, each neuron respectively with two dimensional image f (x, y)
I × J pixel it is corresponding, by xth row, y column pixel pixel value is used as marked as xth row, the neural network of y column
The outside stimulus I of neuronxyIt is sent into PCNN, obtains image segmentation result RE, RE is a two values matrix;
(9.2), edge contour is asked to two values matrix RE, obtains defect characteristic.
Goal of the invention of the invention is achieved in that
The present invention is based on the thermal-induced imagery defect characteristic recognition methods of dynamic multi-objective optimization, by thermal image sequence
Transformation step-length selects the transient thermal response of pixel, and is classified using FCM, obtains the transient thermal response of each pixel
Generic, then consider pixel value (temperature value) similitude of each classification pixel Yu similar pixel, consider simultaneously
The otherness of the pixel (temperature spot) and different classes of pixel (temperature spot) constructs corresponding multiple objective function, meanwhile,
After every secondary environment changes, by forecasting mechanism, channeling direction is provided for Evolution of Population, helps multi-objective optimization algorithm to new
Quick response is made in variation, by multi-objective optimization algorithm, obtains the dimensionality reduction of thermal image sequence as a result, finally utilizing pulse-couple
Neural network carries out feature identification, to identify the defect characteristic of thermal-induced imagery.Through the above steps, it realizes and represents transient state
The accurate selection of hot corresponding (temperature spot), ensure that the precision of defect characteristic identification, while reducing and obtaining under dynamic environment
Each classification information represents thermal transient and calculates consumption accordingly.
Meanwhile also having the present invention is based on the thermal-induced imagery defect characteristic recognition methods of dynamic multi-objective optimization and following have
Beneficial effect:
1, the present invention realizes the comprehensive consideration of otherness and similitude using Multipurpose Optimal Method, and accurately portrays
Defect profile compensates for conventional method for some shortcomings in dimension-reduction treatment, and the algorithm than being based only on otherness identifies defect
Feature is more representative;
2, the present invention uses multi-direction predicting strategy, introduces multiple transient thermal responses that represent and suitably describes PS (Pareto
Set shape) records the distribution situation of every secondary environment PS, and the new position of PS is predicted with this.After variation has occurred in environment,
The new position that PS is predicted with the representative transient thermal response of preceding two secondary environment generates several new initial population transient states in new position
Thus thermal response accelerates the response to environmental change.
Detailed description of the invention
Fig. 1 is a kind of specific implementation of thermal-induced imagery defect characteristic recognition methods the present invention is based on dynamic multi-objective optimization
The flow chart of mode;
Fig. 2 is to carry out sorted result figure using transient thermal response of the fuzzy C-means clustering to selection;
Fig. 3 is the transient thermal response curve graph of material self-temperature point;
Fig. 4 is the transient thermal response curve graph of 1 temperature spot of defect;
Fig. 5 is the transient thermal response curve graph of 2 temperature spot of defect;
Fig. 6 is the transient thermal response curve graph for the respective material self-temperature point chosen based on otherness;
Fig. 7 is the transient thermal response curve graph for 1 temperature spot of correspondence defect chosen based on otherness;
Fig. 8 is the transient thermal response curve graph for 2 temperature spot of correspondence defect chosen based on otherness;
Fig. 9 is the transient thermal response curve graph for the respective material self-temperature point chosen based on the present invention;
Figure 10 is the transient thermal response curve graph for 1 temperature spot of correspondence defect chosen based on the present invention;
Figure 11 is the transient thermal response curve graph for 2 temperature spot of correspondence defect chosen based on the present invention;
Figure 12 is the defect characteristic figure identified based on the present invention.
Specific embodiment
A specific embodiment of the invention is described with reference to the accompanying drawing, preferably so as to those skilled in the art
Understand the present invention.Requiring particular attention is that in the following description, when known function and the detailed description of design perhaps
When can desalinate main contents of the invention, these descriptions will be ignored herein.
Fig. 1 is a kind of specific implementation of thermal-induced imagery defect characteristic recognition methods the present invention is based on dynamic multi-objective optimization
The flow chart of mode.
In the present embodiment, as shown in Figure 1, the present invention is based on the knowledges of the thermal-induced imagery defect characteristic of dynamic multi-objective optimization
Other method the following steps are included:
Step S1: thermal image sequence is expressed as three-dimensional matrice
The thermal image sequence that thermal infrared imager obtains is indicated with three-dimensional matrice S, element S (i, j, t) therein indicates heat
The pixel value that i-th row of the t frame thermal image of image sequence, jth arrange.
Step S2: max pixel value is selected
Max pixel value S (i is selected from three-dimensional matrice Szz,jzz,tzz), wherein izz、jzzAnd tzzRespectively indicate maximum pixel
It is worth pixel line number, the columns of column and the frame number of place frame of the row.
Step S3: it divides trip data block and calculates its row step-length
For the t of three-dimensional matrice SzzFrame chooses jthzzRow chooses P picture according to the variation of pixel value (i.e. temperature value)
Element value trip point, trip point are located between two jump pixel value pixels, are drawn by row to three-dimensional matrice S with trip point
Point, obtain P+1 row data block;
In p-th of row data block SpIn (p=1,2 ..., P+1), find max pixel value, be denoted asIts
In,Respectively indicate p-th of row data block SpThe columns of middle max pixel value pixel line number of the row, column
And the frame number of place frame, then max pixel valueCorresponding transient thermal response isT=1,
2 ..., T, T are the total quantity of three-dimensional matrice S frame;
P-th of row data block S is setpTemperature threshold be THREp, calculate transient thermal responseMost with distance
Big pixel value, that is, temperature maximumPixel column from the near to the distant ring by the corresponding thermal transient of pixel pixel value
It answersBetween degree of correlation Reb, b successively takes 1,2 ..., and judges degree of correlation RebWhether temperature threshold is less than
THREp, when being less than, stop calculating, at this point, pixel spacing b is p-th of row data block row data block SpRow step-length, be denoted as
CLp。
Step S4: it divides dequeued data block and calculates its column step-length
For the t of three-dimensional matrice SzzFrame chooses i-thzzRow chooses Q picture according to the variation of pixel value (i.e. temperature value)
Element value trip point, trip point are located between two jump pixel value pixels, are drawn by column to three-dimensional matrice S with trip point
Point, obtain Q+1 column data block;
In q-th of column data block SqIn (q=1,2 ..., Q+1), find max pixel value, be denoted asIts
In,Respectively indicate q-th of column data block SqThe columns of middle max pixel value pixel line number of the row, column
And the frame number of place frame, then max pixel valueCorresponding transient thermal response isT=1,
2 ..., T, T are the total quantity of three-dimensional matrice S frame;
Q-th of column data block S is setqTemperature threshold be THREq, calculate transient thermal responseMost with distance
Big pixel value, that is, temperature maximumThe pixel corresponding thermal transient of pixel pixel value from the near to the distant of being expert at is rung
It answersBetween degree of correlation Red, d successively takes 1,2 ..., and judges degree of correlation RedWhether temperature threshold is less than
THREq, when being less than, stop calculating, at this point, pixel spacing d is d-th of column data block SqColumn step-length, be denoted as CLq。
Step S5: piecemeal substep is long to choose transient thermal response
Step S5.1: the Q pixel value chosen according to the step S3 P pixel value trip point chosen by column and step S4
Trip point carries out piecemeal to three-dimensional matrice S by row, obtains a data block of (P+1) × (Q+1), pth, upper q-th of the data of column on row
Block is expressed as Sp,q;
Step S5.2: for each data block Sp,q, threshold value DD is set, set number g=1, initialized pixel point are initialized
Position i=1, j=1, and by max pixel value S (izz,jzz,tzz) corresponding transient thermal response S (izz,jzz, t), t=1,
2 ..., T, is stored in set X (g);Then data block S is calculatedp,qMiddle pixel is located at i row, the transient thermal response S of j columnp,q
(i, j, t), t=1, the degree of correlation Rei between 2 ..., T, with set X (g),j, and judge:
If Rei,j< DD, then g=g+1, and by transient thermal response Sp,q(i, j, t), t=1,2 ..., T are new as one
Characteristic storage is in set X (g);Otherwise, i=i+CL is enabledp, continue to calculate next transient thermal response Sp,q(i, j, t), t=1,
2 ..., the degree of correlation of T and set X (g);If i > Mp,q, then i=i-M is enabledp,q, j=j+CLq, that is, change to jth+CLqArrange into
Row calculates, if j > Np,q, then transient thermal response is chosen and is finished, wherein Mp,q、Np,qRespectively data block Sp,qLine number, column
Number.
Step S6: classified using transient thermal response of the fuzzy C-means clustering to selection
All set X (g) i.e. transient thermal response of the step S5 all a data blocks of (P+1) × (Q+1) chosen is used
FCM (fuzzy C-means clustering) algorithm is divided into L class, obtains classification belonging to each transient thermal response.
In the present embodiment, specifically, comprising the following steps:
Step S6.1: setting clusters number L, the number of iterations c=0 is initialized, setting terminates iterated conditional threshold epsilon;
Step S6.2: formula is utilizedCalculate subordinated-degree matrix U;
Wherein, i'=1,2 ..., L, c ∈ L,n'dk'=| | xk'-i'V | |, n'=i', j',n'dk'Indicate kth ' a pixel
With the i-th ' cluster centrei'The Euclidean distance of V, xk'Indicate the coordinate of kth ' a pixel;τ is constant;i'uk'Indicate kth ' a picture
Vegetarian refreshments is under the jurisdiction of the degree of the i-th ' class;
Step S6.3: cluster centre is updatedi'V
Wherein,Indicate the thermal response value of kth ' a pixel;
Step S6.4: if the difference absolute value that the number of iterations reaches maximum value L or front and back cluster centre twice is less than ε,
Then algorithm terminates, and exports subordinated-degree matrix U and cluster centre V, enters back into step step S6.5;Otherwise, c=c+1 is enabled, is returned
Step S6.2;
Step S6.5: criterion is maximized to all pixels point de-fuzzy using degree of membership, is obtained belonging to each pixel
Classification, i.e. Mk'=argi'max(i'uk')。
Step S7: the representative of every class transient thermal response is chosen based on dynamic multi-objective, and constitutes matrix Y
Step S7.1: under the m+1 times external environment, a class transient thermal response of i-th ' (i'=1 ..., L) is selected and is represented
When, define multiple objective function:
Wherein,The transient thermal response selected for the i-th ' class transient thermal response under the m+1 times external environmentClass in Euclidean distance, indicate are as follows:
The transient thermal response selected for the i-th ' class transient thermal responseL-1 class
Between Euclidean distance, Euclidean distance between L-1 class calculatedComposition is renumberd,It indicates are as follows:
For transient thermal responseIn pixel value, that is, temperature value of t moment,For the i-th ' class thermal transient
Respond cluster centre t moment pixel value, that is, temperature value,It is jth ' class transient thermal response cluster centre in t
Pixel value, that is, the temperature value at moment;
The multiple objective function approximation forward position disaggregation obtained under step S7.2: the m-1 times and m secondary environment is respectively
WithCorresponding population transient thermal response (temperature spot) disaggregation is respectivelyWithIts number is respectivelyWithAfter environmental change, according to the m-1 times and the historical information of m secondary environment, prediction calculates close under m+1 secondary environment
Like the initialization population transient thermal response of forward position disaggregation, steps are as follows:
Step S7.2.1:Be fromSolution concentrates random selection NEA transient thermal responseThe thermal transient of composition is rung
It should collect, n'=1,2 .., NE, calculateThe number W for representing transient thermal response is concentrated, it is more under m+1 secondary environment for obtaining
Direction prediction collection:
Wherein, W1And W2It is W lower limit value and upper limit value respectively, and has W1=L+1, W2=3L,It is the variation of m secondary environment
The assessed value of degree, is obtained by following formula:
Wherein,Be fromSolution concentrates random selection NEA transient thermal responseThe transient thermal response of composition
Collection, n'=1,2 .., NE;
Step S7.2.2: selection W represent transient thermal response
A), when initial, the multi-direction forecast set of PS of transient thermal response composition is representedConsist of two parts:
First is thatThe center of disaggregation transient thermal response, is denoted as
Wherein,For disaggregationIn n-th of transient thermal response;
Second is that PF (the optimal forward position the Pareto) minimax solution obtained under m secondary environment, is denoted asL'
For the number of minimax solution;
At this point, setThe middle number for representing transient thermal responseFor L'+1;
Calculate disaggregationIn n-th of transient thermal responseTo setIn respectively represent transient state
Thermal responseEuclidean distanceAnd it will be each according to Euclidean distanceIt is divided into apart from the smallest cluster set represented where transient thermal responseIn;
C) if,Then exportAnd cluster resultIfIt needs to increase newly and represents transient thermal responseIt is rung as thermal transient is represented
Set should be stored inIn,It is obtained by following formula:
Wherein,It isA cluster resultRepresentative transient state
Thermal response,It isA cluster resultRepresent transient state k-th
Thermal response;Find each cluster resultMiddle transient thermal responseTransient state is represented with corresponding
Thermal responseThe maximum transient thermal response of distance, such a cluster result just obtains one apart from maximum thermal transient
Then response, total W find one apart from maximum transient thermal response at this W again and maximum represent thermal transient as increasing newly
ResponseThen return step C);
Step S7.2.3: according to the multi-direction forecast set of the PS of the m-1 times and m secondary environmentWithWherein,It presses
It is obtained according to the method for step S7.2.1, S7.2.2, W' isConcentrate the number for representing transient thermal response;
Calculate prediction direction
Wherein,It is the multi-direction forecast set of PSIn withApart from nearest transient thermal response, serial number
For h';
Step S7.2.4: when the number of iterations g'=0, the initialization population wink of the approximate forward position disaggregation under m+1 secondary environment
State thermal response number is Np, whereinA initial population transient thermal response generates at random in value range,
A initial population transient thermal response is predicted to obtain by following formula:
Wherein, wnFor transient thermal responseAffiliated cluster resultSerial number,It is one to obey
Value is 0, and variance isNormal distribution random number, varianceCalculation formula are as follows:
In the present invention, due to according to the historical information under environment before this, obtaining the approximate forward position solution under m+1 secondary environment
The initialization population transient thermal response of collection provides channeling direction for Evolution of Population, multi-objective optimization algorithm is helped to do new change
Quick response out.
S7.3: initialization relevant parameter
Initialize the number of iterations g'=0, one group of equally distributed weight vectorsWherein,
Initialized reference point
It is functionCorresponding reference point;Maximum number of iterations g'max;
The evolutionary rate for initializing each population transient thermal response isPopulation thermal transient is rung
The global optimum answered and local best-fit
S7.4: it utilizesConstruct the dynamic mesh of each population transient thermal response under Tchebycheff polymerization
Scalar functions fitness value
S7.5: to n=1 ..., NP: according to particle swarm algorithm renewal speedWith population transient thermal responseCompare according to multi-objective optimization algorithmUpdate global optimumLocal optimumAnd reference pointFromMiddle reservation dominatesSolution vector, remove all quiltsThe solution vector of domination, ifIn vector all
It does not dominateIt willIt is addedN=n+1 simultaneously, if n≤NP, then g'=g'+1;
S7.6: it evolves and terminates judgement: if g'≤g'max, then repeatedly step S7.5, if g'> g'max, then the i-th ' class temperature is obtained
Spend the final forward position approximation disaggregation of transient thermal response
S7.7: from forward position approximate solution collectionSelect the representative of the i-th ' class transient thermal responsei'REP, the transient state of all L classes
Thermal response, which is represented, places (one is classified as the pixel value i.e. temperature value at T moment) by column, constitutes the matrix Y of a T × L;
Step S8: three-dimensional matrice S is become into two-dimensional matrix, and linear transformation is carried out to it with matrix Y and obtains two dimension
A two dimensional image f (x, y) of image array R and pixel value (temperature value) disparity:
By each frame in three-dimensional matrice S since first row, latter column are connect at the end of previous column, new one is constituted
Column, obtain the corresponding T column pixel value of T frame, and then, according to time order and function, T column pixel value is sequentially placed, constitutes I × J row, T
Column two dimensional image matrix O carries out linear transformation to two-dimensional matrix O with matrix Y, it may be assumed thatObtain two dimensional image matrix
R, whereinIt is the pseudo inverse matrix of matrix Y, O for L × T matrixTThe transposed matrix of two dimensional image matrix O, obtained two dimensional image
Matrix R is L row, I × J column;
Every a line of two dimensional image matrix R is intercepted by J Leie, and the J of interception is arranged to be sequentially placed by row, constitutes one
I × J two dimensional image is opened, such L row obtains L I × J two dimensional images, these pictures all contain defect area, for convenience of lacking
Outline identification is fallen into, a two dimensional image of defect area and non-defective region pixel value (temperature value) disparity is selected, and is remembered
For f (x, y).
Step S9: feature identification is carried out to two dimensional image f (x, y) using Pulse Coupled Neural Network (PCNN), is lacked
Fall into feature
Step S9.1: one PCNN network by I × J neuron of construction, each neuron respectively with two dimensional image f
I × J the pixel of (x, y) is corresponding, and by xth row, y column pixel pixel value is used as marked as xth row, the mind of y column
Outside stimulus I through network neural memberxyIt is sent into PCNN, obtains image segmentation result RE, RE is a two values matrix;
Step S9.2:, edge contour is asked to two values matrix RE, obtain defect characteristic.
Example
In the present embodiment, there are two types of defects on test specimen, i.e., thermally conductive without the defect 1 and filling of filling any material
The defect 2 of property difference material.
In the present embodiment, sorted result figure is carried out such as using transient thermal response of the fuzzy C-means clustering to selection
Shown in Fig. 2.
Three known temperature points of Direct Recognition in the thermal imagery graphic sequence of test specimen, i.e. material self-temperature point, 1 temperature of defect
The transient thermal response curve of point and 2 temperature spot of defect, is denoted as respectivelyBacPOINT、Def1POINT andDef2POINT, as Fig. 3,
4, shown in 5.
With the existing method for selecting transient thermal response to represent based on otherness, obtains three transient thermal responses and represents:ANFCM23、BNFCM68AndcNFCM79, they respectively correspond material self-temperature point, 2 temperature of 1 temperature spot of defect and defect
Point, curve is as shown in Fig. 6,7,8.
The method for selecting transient thermal response to represent with dynamic multi-objective optimization in the present invention, obtains three transient thermal response generations
Table:ANFCM25、BNFCM66AndcNFCM25, they respectively correspond 2 temperature of material self-temperature point, 1 temperature spot of defect and defect
Point is spent, curve is as shown in Fig. 9,10,11.
From thermal response curve: 1 temperature spot of defect has apparent downward trend, the amplitude temperature of 2 temperature spot of defect
It is minimum.Three features are compared, and 1 temperature spot heat release of defect is most fast, and 2 temperature spot of defect is most slow.
Transient thermal response curve under two methods with directly from the corresponding transient thermal response curve of thermography recognition sequence
The degree of correlation is as shown in table 1.
Self-temperature point | 1 temperature spot of defect | 2 temperature spot of defect | |
Based on the method for difference | 0.9976 | 0.9954 | 0.9966 |
The present invention | 0.9989 | 0.9959 | 0.9971 |
Table 1
From table 1, it can be seen that the correlation for the transient thermal response curve that the method for the present invention is chosen is more preferable.
In the present embodiment, the defect characteristic of identification is as shown in figure 12.
Although the illustrative specific embodiment of the present invention is described above, in order to the technology of the art
Personnel understand the present invention, it should be apparent that the present invention is not limited to the range of specific embodiment, to the common skill of the art
For art personnel, if various change the attached claims limit and determine the spirit and scope of the present invention in, these
Variation is it will be apparent that all utilize the innovation and creation of present inventive concept in the column of protection.
Claims (1)
1. a kind of thermal-induced imagery defect characteristic recognition methods based on dynamic multi-objective optimization, which is characterized in that including following
Step:
(1), the thermal image sequence that thermal infrared imager obtains is indicated with three-dimensional matrice S, element S (i, j, t) therein indicates heat
The pixel value that i-th row of the t frame thermal image of image sequence, jth arrange;
(2), max pixel value S (i is selected from three-dimensional matrice Szz,jzz,tzz), wherein izz、jzzAnd tzzRespectively indicate maximum pixel
It is worth pixel line number, the columns of column and the frame number of place frame of the row;
(3), for the t of three-dimensional matrice SzzFrame chooses jthzzRow chooses P pixel according to the variation of pixel value (i.e. temperature value)
It is worth trip point, trip point is located between two jump pixel value pixels, three-dimensional matrice S divided by row with trip point,
Obtain P+1 row data block;
In p-th of row data block SpIn (p=1,2 ..., P+1), find max pixel value, be denoted asWherein,Respectively indicate p-th of row data block SpMiddle max pixel value pixel line number of the row, column columns and
The frame number of place frame, then max pixel valueCorresponding transient thermal response is
T is the total quantity of three-dimensional matrice S frame;
P-th of row data block S is setpTemperature threshold be THREp, calculate transient thermal responseWith the maximum picture of distance
Element value is temperature maximumThe pixel column corresponding transient thermal response of pixel pixel value from the near to the distantBetween degree of correlation Reb, b successively takes 1,2 ..., and judges degree of correlation RebWhether temperature threshold is less than
THREp, when being less than, stop calculating, at this point, pixel spacing b is p-th of row data block row data block SpRow step-length, be denoted as
CLp;
(4), for the t of three-dimensional matrice SzzFrame chooses i-thzzRow chooses Q pixel according to the variation of pixel value (i.e. temperature value)
It is worth trip point, trip point is located between two jump pixel value pixels, three-dimensional matrice S divided by column with trip point,
Obtain Q+1 column data block;
In q-th of column data block SqIn (q=1,2 ..., Q+1), find max pixel value, be denoted asWherein,Respectively indicate q-th of column data block SqMiddle max pixel value pixel line number of the row, column columns and
The frame number of place frame, then max pixel valueCorresponding transient thermal response isT
For the total quantity of three-dimensional matrice S frame;
Q-th of column data block S is setqTemperature threshold be THREq, calculate transient thermal responseWith apart from maximum pixel
Value is temperature maximumPixel is expert at the corresponding transient thermal response of pixel pixel value from the near to the distantBetween degree of correlation Red, d successively takes 1,2 ..., and judges degree of correlation RedWhether temperature threshold is less than
THREq, when being less than, stop calculating, at this point, pixel spacing d is d-th of column data block SqColumn step-length, be denoted as CLq;
(5), piecemeal substep is long chooses transient thermal response
(5.1), the K pixel value jump that the P pixel value trip point chosen according to step (3) is chosen by column and step (4)
It presses row and piecemeal is carried out to three-dimensional matrice S, obtain a data block of (P+1) × (Q+1), pth, upper q-th of data block table of column on row
It is shown as Sp,q;
(5.2), for each data block Sp,q, threshold value DD is set, set number g=1, initialized pixel point position i=are initialized
1, j=1, and by max pixel value S (izz,jzz,tzz) corresponding transient thermal response S (izz,jzz, t), t=1,2 ..., T are deposited
Storage is in set X (g);Then data block S is calculatedp,qMiddle pixel is located at i row, the transient thermal response S of j columnp,q(i, j, t), t=
Degree of correlation Re between 1,2 ..., T, with set X (g)i,j, and judge:
If Rei,j< DD, then g=g+1, and by transient thermal response Sp,q(i, j, t), t=1,2 ..., T are as a new feature
It is stored in set X (g);Otherwise, i=i+CL is enabledp, continue to calculate next transient thermal response Sp,q(i, j, t), t=1,
2 ..., the degree of correlation of T and set X (g);If i > Mp,q, then i=i-M is enabledp,q, j=j+CLq, that is, change to jth+CLqArrange into
Row calculates, if j > Np,q, then transient thermal response is chosen and is finished, wherein Mp,q、Np,qRespectively data block Sp,qLine number, column
Number;
(6), all set X (g) the i.e. transient thermal response for all a data blocks of (P+1) × (Q+1) that step (5) are chosen is used
FCM (fuzzy C-means clustering) algorithm is divided into L class, obtains classification belonging to each transient thermal response;
(7), the representative of every class transient thermal response is chosen based on dynamic multi-objective, and constitutes matrix Y
(7.1), under the m+1 times external environment, when being represented to the choosing of a class transient thermal response of i-th ' (i'=1 ..., L), definition
Multiple objective function:
Wherein,The transient thermal response selected for the i-th ' class transient thermal response under the m+1 times external environment
Class in Euclidean distance, indicate are as follows:
The transient thermal response selected for the i-th ' class transient thermal responseL-1 class between Europe
Family name's distance, Euclidean distance between L-1 class calculatedComposition is renumberd,It indicates are as follows:
For transient thermal responseIn pixel value, that is, temperature value of t moment,For the i-th ' class transient thermal response
Cluster centre t moment pixel value, that is, temperature value,It is jth ' class transient thermal response cluster centre in t moment
Pixel value, that is, temperature value;
(7.2), the multiple objective function approximation forward position disaggregation obtained under the m-1 times and m secondary environment is respectivelyWith
Corresponding population transient thermal response (temperature spot) disaggregation is respectivelyWithIts number is respectivelyWith?
After environmental change, according to the m-1 times and the historical information of m secondary environment, prediction calculates the approximate forward position solution under m+1 secondary environment
The initialization population transient thermal response of collection, steps are as follows:
(7.2.1)、Be fromSolution concentrates random selection NEA transient thermal responseThe transient thermal response collection of composition, n'
=1,2 .., NE, calculateThe number W for representing transient thermal response is concentrated, for obtaining multi-direction prediction under m+1 secondary environment
Collection:
Wherein, W1And W2It is W lower limit value and upper limit value respectively, and has W1=L+1, W2=3L,It is m secondary environment variation degree
Assessed value, obtained by following formula:
Wherein,Be fromSolution concentrates random selection NEA transient thermal responseThe transient thermal response collection of composition, n'
=1,2 .., NE;
(7.2.2), selection W represents transient thermal response
A), when initial, the multi-direction forecast set of PS of transient thermal response composition is representedConsist of two parts:
First is thatThe center of disaggregation transient thermal response, is denoted as
Wherein,For disaggregationIn n-th of transient thermal response;
Second is that PF (the optimal forward position the Pareto) minimax solution obtained under m secondary environment, is denoted asL' is extreme value
The number of solution;
At this point, setThe middle number for representing transient thermal responseFor L'+1;
B), disaggregation is calculatedIn n-th of transient thermal responseTo setIn respectively represent transient state
Thermal responseEuclidean distanceAnd it will be each according to Euclidean distanceIt is divided into apart from the smallest cluster set represented where transient thermal responseIn;
C) if,Then exportAnd cluster resultIfIt needs to increase newly and represents transient thermal responseGather as transient thermal response deposit is representedIn,
It is obtained by following formula:
Wherein,It isA cluster resultRepresentative thermal transient ring
It answers,It isA cluster resultThe thermal transient that represents for k-th ring
It answers;Find each cluster resultMiddle transient thermal responseIt is rung with the corresponding thermal transient that represents
It answersThe maximum transient thermal response of distance, such a cluster result just obtains one apart from maximum transient thermal response,
Then total W finds one apart from maximum transient thermal response at this W again and maximum as newly-increased represents transient thermal responseThen return step C);
(7.2.3), the multi-direction forecast set of PS according to the m-1 times and m secondary environmentWithWherein,According to step (7.2.1), the side of (7.2.2)
Method obtains, and W' isConcentrate the number for representing transient thermal response;
Calculate prediction direction
Wherein,It is the multi-direction forecast set of PSIn withApart from nearest transient thermal response, serial number h';
When (7.2.4), the number of iterations g'=0, the initialization population transient thermal response of the approximate forward position disaggregation under m+1 secondary environment
Number is Np, whereinA initial population transient thermal response generates at random in value range,A initial kind
Group's transient thermal response is predicted to obtain by following formula:
Wherein, wnFor transient thermal responseAffiliated cluster resultSerial number,It is that an obedience mean value is
0, variance isNormal distribution random number, varianceCalculation formula are as follows:
(7.3), relevant parameter is initialized
Initialize the number of iterations g'=0, one group of equally distributed weight vectorsWherein,
Initialized reference point It is letter
NumberCorresponding reference point;Maximum number of iterations g'max;
The evolutionary rate for initializing each population transient thermal response isPopulation transient thermal response
Global optimum and local best-fit
(7.4), it utilizesConstruct the dynamic object letter of each population transient thermal response under Tchebycheff polymerization
Number fitness value
(7.5), to n=1 ..., NP: according to particle swarm algorithm renewal speedWith population transient thermal responseCompare according to multi-objective optimization algorithmUpdate global optimumLocal optimumAnd reference pointFromMiddle reservation dominatesSolution vector, remove all quiltsThe solution vector of domination, ifIn vector all
It does not dominateIt willIt is addedN=n+1 simultaneously, if n≤NP, then g'=g'+1;
(7.6), it evolves and terminates judgement: if g'≤g'max, then repeatedly step (7.5), if g'> g'max, then the i-th ' class temperature is obtained
The final forward position approximation disaggregation of transient thermal response
(7.7), from forward position approximate solution collectionSelect the representative of the i-th ' class transient thermal responsei' REP, the thermal transient sound of all L classes
It Ying represent and place (one is classified as the pixel value i.e. temperature value at T moment) by column, constitute the matrix Y of a T × L;
(8), by each frame in three-dimensional matrice S since first row, latter column is connect at the end of previous column, new one is constituted
Column, obtain the corresponding T column pixel value of T frame, and then, according to time order and function, T column pixel value is sequentially placed, constitutes I × J row, T
Column two dimensional image matrix O carries out linear transformation to two-dimensional matrix O with matrix Y, it may be assumed thatObtain two dimensional image matrix
R, whereinIt is the pseudo inverse matrix of matrix Y, O for L × T matrixTThe transposed matrix of two dimensional image matrix O, obtained two dimensional image
Matrix R is L row, I × J column;
Every a line of two dimensional image matrix R is intercepted by J Leie, and the J of interception arrange and is sequentially placed by going, constitute an I ×
J two dimensional image, such L row obtain L I × J two dimensional images, these pictures all contain defect area, for convenience of defect profile
Extract, select defect area and non-defective region pixel value (temperature value) disparity a two dimensional image, and be denoted as f (x,
y);
(9), feature extraction is carried out to two dimensional image f (x, y) using Pulse Coupled Neural Network (PCNN), obtains defect characteristic:
(9.1), a PCNN network by I × J neuron is constructed, each neuron I with two dimensional image f (x, y) respectively
× J pixel is corresponding, and by xth row, y column pixel pixel value is used as marked as xth row, the neural network mind of y column
Outside stimulus I through memberxyIt is sent into PCNN, obtains image segmentation result RE, RE is a two values matrix;
(9.2), edge contour is asked to two values matrix RE, obtains defect characteristic.
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910019827.XA CN109767438B (en) | 2019-01-09 | 2019-01-09 | Infrared thermal image defect feature identification method based on dynamic multi-objective optimization |
US16/370,202 US11036978B2 (en) | 2018-05-29 | 2019-03-29 | Method for separating out a defect image from a thermogram sequence based on weighted naive bayesian classifier and dynamic multi-objective optimization |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910019827.XA CN109767438B (en) | 2019-01-09 | 2019-01-09 | Infrared thermal image defect feature identification method based on dynamic multi-objective optimization |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109767438A true CN109767438A (en) | 2019-05-17 |
CN109767438B CN109767438B (en) | 2021-06-08 |
Family
ID=66453527
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910019827.XA Active CN109767438B (en) | 2018-05-29 | 2019-01-09 | Infrared thermal image defect feature identification method based on dynamic multi-objective optimization |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109767438B (en) |
Cited By (16)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110321871A (en) * | 2019-07-11 | 2019-10-11 | 电子科技大学成都学院 | A kind of palm vein identification system and method based on LSTM |
CN110569616A (en) * | 2019-09-12 | 2019-12-13 | 哈尔滨工业大学 | SOM-based building multi-objective optimization design decision support method |
CN110889437A (en) * | 2019-11-06 | 2020-03-17 | 北京达佳互联信息技术有限公司 | Image processing method and device, electronic equipment and storage medium |
CN111311638A (en) * | 2020-02-11 | 2020-06-19 | 中国人民解放军军事科学院评估论证研究中心 | Dynamic multi-objective optimization method based on segmentation multi-directional prediction strategy |
CN111598887A (en) * | 2020-05-25 | 2020-08-28 | 中国空气动力研究与发展中心超高速空气动力研究所 | Spacecraft defect detection method based on LVQ-GMM algorithm and multi-objective optimization segmentation algorithm |
CN111667466A (en) * | 2020-05-26 | 2020-09-15 | 湖北工业大学 | Multi-objective optimization feature selection method for multi-classification of strip steel surface quality defects |
CN112016628A (en) * | 2020-09-04 | 2020-12-01 | 中国空气动力研究与发展中心超高速空气动力研究所 | Space debris impact damage interpretation method based on dynamic multi-target prediction |
CN112016627A (en) * | 2020-09-04 | 2020-12-01 | 中国空气动力研究与发展中心超高速空气动力研究所 | Visual detection and evaluation method for micro-impact damage of on-orbit spacecraft |
CN112037211A (en) * | 2020-09-04 | 2020-12-04 | 中国空气动力研究与发展中心超高速空气动力研究所 | Damage characteristic identification method for dynamically monitoring small space debris impact event |
CN112215830A (en) * | 2020-10-21 | 2021-01-12 | 中国空气动力研究与发展中心超高速空气动力研究所 | Method for judging impact damage characteristic types of aerospace heat-proof materials |
CN112233099A (en) * | 2020-10-21 | 2021-01-15 | 中国空气动力研究与发展中心超高速空气动力研究所 | Reusable spacecraft surface impact damage characteristic identification method |
CN112784847A (en) * | 2021-01-28 | 2021-05-11 | 中国空气动力研究与发展中心超高速空气动力研究所 | Segmentation and identification method for ultra-high-speed impact damage detection image |
CN112819778A (en) * | 2021-01-28 | 2021-05-18 | 中国空气动力研究与发展中心超高速空气动力研究所 | Multi-target full-pixel segmentation method for aerospace material damage detection image |
CN113538232A (en) * | 2021-06-21 | 2021-10-22 | 电子科技大学 | Large-size aerospace composite material component global defect quantitative identification method |
CN113723433A (en) * | 2021-11-03 | 2021-11-30 | 北京邮电大学 | Multi-target feature selection method and device based on dynamic reference points |
CN114882016A (en) * | 2022-06-30 | 2022-08-09 | 中国矿业大学(北京) | Method and system for identifying concrete defect area based on infrared temperature field time sequence information |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103488851A (en) * | 2013-10-15 | 2014-01-01 | 浙江大学 | Multi-objective optimization method based on geometric structure information |
US8856054B2 (en) * | 2011-01-31 | 2014-10-07 | The Penn State Research Foundation Intellectual Property Offie, The Pennsylvania State University | Evolutionary computing based optimization |
CN105447857A (en) * | 2015-11-17 | 2016-03-30 | 电子科技大学 | Feature extraction method of pulsed eddy-current infrared thermal image |
CN105674326A (en) * | 2016-01-13 | 2016-06-15 | 北京市环境保护科学研究院 | Multi-objective multi-constraint combustion optimization method of industrial gas boiler |
CN103839261B (en) * | 2014-02-18 | 2017-01-25 | 西安电子科技大学 | SAR image segmentation method based on decomposition evolution multi-objective optimization and FCM |
CN107025445A (en) * | 2017-04-10 | 2017-08-08 | 中国科学院合肥物质科学研究院 | Multi-source Remote Sensing Images combination system of selection based on Entropy |
CN107515822A (en) * | 2017-08-16 | 2017-12-26 | 南京大学 | Software defect positioning method based on multiple-objection optimization |
CN107590436A (en) * | 2017-08-10 | 2018-01-16 | 云南财经大学 | Radar emitter signal feature selection approach based on peplomer subgroup multi-objective Algorithm |
CN108765401A (en) * | 2018-05-29 | 2018-11-06 | 电子科技大学 | A kind of thermal imaging testing method based on ranks variable step segmentation and region-growing method |
-
2019
- 2019-01-09 CN CN201910019827.XA patent/CN109767438B/en active Active
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US8856054B2 (en) * | 2011-01-31 | 2014-10-07 | The Penn State Research Foundation Intellectual Property Offie, The Pennsylvania State University | Evolutionary computing based optimization |
CN103488851A (en) * | 2013-10-15 | 2014-01-01 | 浙江大学 | Multi-objective optimization method based on geometric structure information |
CN103839261B (en) * | 2014-02-18 | 2017-01-25 | 西安电子科技大学 | SAR image segmentation method based on decomposition evolution multi-objective optimization and FCM |
CN105447857A (en) * | 2015-11-17 | 2016-03-30 | 电子科技大学 | Feature extraction method of pulsed eddy-current infrared thermal image |
CN105674326A (en) * | 2016-01-13 | 2016-06-15 | 北京市环境保护科学研究院 | Multi-objective multi-constraint combustion optimization method of industrial gas boiler |
CN107025445A (en) * | 2017-04-10 | 2017-08-08 | 中国科学院合肥物质科学研究院 | Multi-source Remote Sensing Images combination system of selection based on Entropy |
CN107590436A (en) * | 2017-08-10 | 2018-01-16 | 云南财经大学 | Radar emitter signal feature selection approach based on peplomer subgroup multi-objective Algorithm |
CN107515822A (en) * | 2017-08-16 | 2017-12-26 | 南京大学 | Software defect positioning method based on multiple-objection optimization |
CN108765401A (en) * | 2018-05-29 | 2018-11-06 | 电子科技大学 | A kind of thermal imaging testing method based on ranks variable step segmentation and region-growing method |
Non-Patent Citations (5)
Title |
---|
P. P. ZHU, C. YIN, Y. H. CHENG, ET AL.: ""An improved feature extraction algorithm for automatic defect identification based on eddy current pulsed thermography"", 《MECHANICAL SYSTEMS AND SIGNAL PROCESSING》 * |
QINGFU ZHANG,HUI LI: ""MOEA/D: A Multiobjective Evolutionary Algorithm Based on Decomposition"", 《IEEE TRANSACTIONS ON EVOLUTIONARY COMPUTATION》 * |
XIANGZHI BAI,ZHIGUO CHEN ET. AL .: ""SPATIAL INFORMATION BASED FCM FOR INFRARED SHIP TARGET SEGMENTATION"", 《IEEE TRANSACTIONS ON CYBERNETICS》 * |
巩方超,王硕禾等: ""基于模糊集和k-means算法的变压器红外图像分割"", 《石家庄铁道大学学报(自然科学版)》 * |
田露露,程玉华等: ""基于涡流磁光成像检测的缺陷图像分割方法"", 《2018 远东无损检测新技术论坛》 * |
Cited By (27)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110321871A (en) * | 2019-07-11 | 2019-10-11 | 电子科技大学成都学院 | A kind of palm vein identification system and method based on LSTM |
CN110569616A (en) * | 2019-09-12 | 2019-12-13 | 哈尔滨工业大学 | SOM-based building multi-objective optimization design decision support method |
CN110569616B (en) * | 2019-09-12 | 2022-06-21 | 哈尔滨工业大学 | SOM-based building multi-objective optimization design decision support method |
CN110889437A (en) * | 2019-11-06 | 2020-03-17 | 北京达佳互联信息技术有限公司 | Image processing method and device, electronic equipment and storage medium |
CN110889437B (en) * | 2019-11-06 | 2022-11-11 | 北京达佳互联信息技术有限公司 | Image processing method and device, electronic equipment and storage medium |
CN111311638A (en) * | 2020-02-11 | 2020-06-19 | 中国人民解放军军事科学院评估论证研究中心 | Dynamic multi-objective optimization method based on segmentation multi-directional prediction strategy |
CN111598887A (en) * | 2020-05-25 | 2020-08-28 | 中国空气动力研究与发展中心超高速空气动力研究所 | Spacecraft defect detection method based on LVQ-GMM algorithm and multi-objective optimization segmentation algorithm |
CN111598887B (en) * | 2020-05-25 | 2023-04-07 | 中国空气动力研究与发展中心超高速空气动力研究所 | Spacecraft defect detection method based on LVQ-GMM algorithm and multi-objective optimization segmentation algorithm |
CN111667466A (en) * | 2020-05-26 | 2020-09-15 | 湖北工业大学 | Multi-objective optimization feature selection method for multi-classification of strip steel surface quality defects |
CN111667466B (en) * | 2020-05-26 | 2023-04-18 | 湖北工业大学 | Multi-objective optimization feature selection method for multi-classification of strip steel surface quality defects |
CN112037211B (en) * | 2020-09-04 | 2022-03-25 | 中国空气动力研究与发展中心超高速空气动力研究所 | Damage characteristic identification method for dynamically monitoring small space debris impact event |
CN112016627B (en) * | 2020-09-04 | 2022-04-19 | 中国空气动力研究与发展中心超高速空气动力研究所 | Visual detection and evaluation method for micro-impact damage of on-orbit spacecraft |
CN112016628A (en) * | 2020-09-04 | 2020-12-01 | 中国空气动力研究与发展中心超高速空气动力研究所 | Space debris impact damage interpretation method based on dynamic multi-target prediction |
CN112016627A (en) * | 2020-09-04 | 2020-12-01 | 中国空气动力研究与发展中心超高速空气动力研究所 | Visual detection and evaluation method for micro-impact damage of on-orbit spacecraft |
CN112037211A (en) * | 2020-09-04 | 2020-12-04 | 中国空气动力研究与发展中心超高速空气动力研究所 | Damage characteristic identification method for dynamically monitoring small space debris impact event |
CN112215830B (en) * | 2020-10-21 | 2022-03-04 | 中国空气动力研究与发展中心超高速空气动力研究所 | Method for judging impact damage characteristic types of aerospace heat-proof materials |
CN112233099B (en) * | 2020-10-21 | 2022-03-25 | 中国空气动力研究与发展中心超高速空气动力研究所 | Reusable spacecraft surface impact damage characteristic identification method |
CN112233099A (en) * | 2020-10-21 | 2021-01-15 | 中国空气动力研究与发展中心超高速空气动力研究所 | Reusable spacecraft surface impact damage characteristic identification method |
CN112215830A (en) * | 2020-10-21 | 2021-01-12 | 中国空气动力研究与发展中心超高速空气动力研究所 | Method for judging impact damage characteristic types of aerospace heat-proof materials |
CN112784847B (en) * | 2021-01-28 | 2022-03-04 | 中国空气动力研究与发展中心超高速空气动力研究所 | Segmentation and identification method for ultra-high-speed impact damage detection image |
CN112819778B (en) * | 2021-01-28 | 2022-04-12 | 中国空气动力研究与发展中心超高速空气动力研究所 | Multi-target full-pixel segmentation method for aerospace material damage detection image |
CN112784847A (en) * | 2021-01-28 | 2021-05-11 | 中国空气动力研究与发展中心超高速空气动力研究所 | Segmentation and identification method for ultra-high-speed impact damage detection image |
CN112819778A (en) * | 2021-01-28 | 2021-05-18 | 中国空气动力研究与发展中心超高速空气动力研究所 | Multi-target full-pixel segmentation method for aerospace material damage detection image |
CN113538232B (en) * | 2021-06-21 | 2023-04-07 | 电子科技大学 | Large-size aerospace composite material component global defect quantitative identification method |
CN113538232A (en) * | 2021-06-21 | 2021-10-22 | 电子科技大学 | Large-size aerospace composite material component global defect quantitative identification method |
CN113723433A (en) * | 2021-11-03 | 2021-11-30 | 北京邮电大学 | Multi-target feature selection method and device based on dynamic reference points |
CN114882016A (en) * | 2022-06-30 | 2022-08-09 | 中国矿业大学(北京) | Method and system for identifying concrete defect area based on infrared temperature field time sequence information |
Also Published As
Publication number | Publication date |
---|---|
CN109767438B (en) | 2021-06-08 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109767438A (en) | A kind of thermal-induced imagery defect characteristic recognition methods based on dynamic multi-objective optimization | |
CN109767437A (en) | Thermal-induced imagery defect characteristic extracting method based on k mean value dynamic multi-objective | |
CN109559309A (en) | Based on the multiple-objection optimization thermal-induced imagery defect characteristic extracting method uniformly evolved | |
CN110598736B (en) | Power equipment infrared image fault positioning, identifying and predicting method | |
CN109544546A (en) | A kind of thermal-induced imagery defect characteristic extracting method based on multiple-objection optimization | |
CN109684922B (en) | Multi-model finished dish identification method based on convolutional neural network | |
CN109118564A (en) | A kind of three-dimensional point cloud labeling method and device based on fusion voxel | |
CN105913040B (en) | The real-time pedestrian detecting system of dual camera under the conditions of noctovision | |
CN108564565A (en) | A kind of power equipment infrared image multi-target orientation method based on deep learning | |
CN105389562B (en) | A kind of double optimization method of the monitor video pedestrian weight recognition result of space-time restriction | |
CN103440505B (en) | The Classification of hyperspectral remote sensing image method of space neighborhood information weighting | |
CN109598711A (en) | A kind of thermal image defect extracting method based on feature mining and neural network | |
CN110570363A (en) | Image defogging method based on Cycle-GAN with pyramid pooling and multi-scale discriminator | |
Mudda et al. | Brain tumor classification using enhanced statistical texture features | |
CN112818822B (en) | Automatic identification method for damaged area of aerospace composite material | |
CN106557740B (en) | The recognition methods of oil depot target in a kind of remote sensing images | |
CN111639587B (en) | Hyperspectral image classification method based on multi-scale spectrum space convolution neural network | |
CN106951915A (en) | A kind of one-dimensional range profile multiple Classifiers Combination method of identification based on classification confidence level | |
CN114627447A (en) | Road vehicle tracking method and system based on attention mechanism and multi-target tracking | |
CN109816638A (en) | Defect extracting method based on dynamic environment feature and weighting Bayes classifier | |
CN106778680A (en) | A kind of hyperspectral image band selection method and device extracted based on critical bands | |
CN112819775A (en) | Segmentation and reinforcement method for damage detection image of aerospace composite material | |
CN106651834A (en) | Method and device for evaluating quality of substation equipment infrared thermal image with no reference image | |
CN108765401B (en) | A kind of thermal imaging testing method based on ranks variable step segmentation and region-growing method | |
CN109872319A (en) | A kind of thermal image defect extracting method based on feature mining and neural network |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |